RecogHypertension: early recognition of hypertension based on heart rate variability

In recent years, the number of patients with hypertension is increasing, but the early symptoms of hypertension are not obvious, the incubation period is long, and the awareness rate and control rate are very low. Therefore, it is necessary to study the early recognition of hypertension in a non-clinical environment. The blood pressure of human being is controlled by autonomic nervous system, and heart rate variability (HRV) is an impact of autonomic nervous system and an indicator of the balance of cardiac sympathetic nerve and vagus nerve. So HRV is good method to recognize the hypertensive patients from healthy person. In this paper, we proposed a fined-grained HRV analysis method to recognize hypertensive patients from healthy person. Specifically, we cut the 8 h of ECG data into 5 min segments at first, and then we propose an improved heartbeat interval extraction algorithm to extract the heartbeat interval from Electrocardiogram (ECG) data and we extract 22 HRV features in linear, nonlinear domain and histogram, Specially, we model the distribution of the heartbeat interval of each time window using a Gaussian mixture model. Next we analyzed the correlation between linear domain and nonlinear domain features of heart rate variability. Finally, we use common machine learning algorithms to train a recognition model for hypertension. In this paper, we use 138 hypertension patients' and 138 healthy person real-world clinical Electrocardiogram data as our data set. The recognition precision rate for patients with hypertension is 97.1%, and the recall rate is 97.1%. The experimental results validate the effectiveness and reliability of the proposed recognition method in this research.